Application of Recurrent Neural Network in Time Series Forecasting for Construction Cost and Duration Focusing on Road Infrastructure in Metro Manila

DOI

10.2991/978-94-6463-926-1_2How to use a DOI?

Keywords

Artificial Neural Networks (ANN); Levenberg-Marquardt Training (LMA); Nonlinear Autoregressive Network With Exogenous Inputs (NARX); Recurrent Neural Networks (RNN); Support Vector Machines (SVM)

Abstract

The challenges in estimating the process and the cost of road and highway construction projects in Metro Manila, which is plagued by extreme traffic congestion and inadequate road quality, are the subject of this study. Due to their inability to take into account the particular unpredictability of each project, traditional scheduling systems like PERT, Critical Path, and Gantt Charting frequently fall short. The study investigates how project forecasting accuracy could be improved by using Artificial Neural Networks (ANNs) and Recurrent Neural Networks (RNNs). The research intends to construct models that more accurately estimate project duration and cost by utilizing RNNs’ power in handling sequential data and ANNs’ capacity to interpret incomplete datasets. The effect of traffic density on these projections is also examined in the study. The research compares the effectiveness of these neural network models to conventional forecasting techniques using historical data from completed road projects in Metro Manila. According to the results, the use of advanced neural network models can greatly increase forecasting accuracy, which would help with resource allocation and project management for road infrastructure projects in Manila. It is advised that more studies be done to improve these models and examine how well they work in various project types and geographical situations.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Jongson V. Balubar
AU  - Marco Raphael L. Mendoza
AU  - Christ John L. Marcos
AU  - Kassandra Ghake C. Dionisio
PY  - 2025
DA  - 2025/12/31
TI  - Application of Recurrent Neural Network in Time Series Forecasting for Construction Cost and Duration Focusing on Road Infrastructure in Metro Manila
BT  - Proceedings of the International Conference on Applied Science and Technology on Engineering Science 2025 (iCAST-ES 2025)
PB  - Atlantis Press
SP  - 4
EP  - 13
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-926-1_2
DO  - 10.2991/978-94-6463-926-1_2
ID  - Balubar2025
ER  -